CN105761308A - Ground LiDAR and image data fused occlusion region building facade reconstruction method - Google Patents
Ground LiDAR and image data fused occlusion region building facade reconstruction method Download PDFInfo
- Publication number
- CN105761308A CN105761308A CN201610113150.2A CN201610113150A CN105761308A CN 105761308 A CN105761308 A CN 105761308A CN 201610113150 A CN201610113150 A CN 201610113150A CN 105761308 A CN105761308 A CN 105761308A
- Authority
- CN
- China
- Prior art keywords
- facade
- geometry
- image
- cloud data
- cloud
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
Abstract
The invention relates to a ground LiDAR and image data fused occlusion region building facade reconstruction method, which comprises a first step of reconstructing a building facade initial model by using LiDAR point cloud data; a second step of refining the building facade initial model combining image data; a third step of conducting an analysis of building facade structure rules and making a prediction of an occlusion region geometry; and a step 4 of verifying the rationality and reliability of the occlusion region geometry using point cloud data. The invention refines the initial facade geometric model reconstructed with the point cloud data by using image data, solves the problems of there being a plurality of candidate image edges in a searching region in the model edge and image edge matching process, obtains an optimal corresponding image edge, and effectively reduces the facade geometry offset caused by the resolution of a laser scanner. Meanwhile, the reliability of occlusion region facade reconstruction is improved.
Description
Technical field
The present invention relates to a kind of building facade method for reconstructing, especially relate to the occlusion area building facade method for reconstructing of a kind of ground LiDAR and image data fusion.
Background technology
Streetscape building facade subtle three-dimensional model is precise path planning, high accuracy outdoor scene location and navigation key foundation data.For streetscape building facade D geometry constraint, all can be obtained the space three-dimensional cloud data of street architecture thing facade by image dense Stereo Matching or ground LiDAR.Research shows that image and LiDAR data have good complementarity in building facade reconstruction, LiDAR point cloud data can ensure that reliable region feature extracts, image data can acquire high-precision structure limit, both combinations greatly improve the geometric accuracy that building facade is rebuild, it also avoid thing side's location difficulty that Image Matching unsuccessfully causes simultaneously, and from the LiDAR point cloud data of unordered, Density inhomogeneity in a large number, express the difficulty of building facade geometry.But, to rebuild building facade complete, reliable from LiDAR and image data and still face the challenge, an important bottleneck problem is how to rebuild the building facade geometry (window, door and balcony etc.) of occlusion area.Due to the restriction at visual angle, occlusion area data cannot obtain, and the building facade geometry of disappearance is generally assumed or under certain rule, reasoning obtains certain, and the reliability of reconstruction is difficult to ensure that.
The occlusion area building facade geometry reconstruction of LiDAR and image data fusion relates generally to occlusion area data filling and two aspects rebuild by facade geometry.In occlusion area data filling, certain methods adopts the mode Resurvey occlusion area cloud data such as handheld laser scanner, stereoscopic vision, fills the cavity of legacy data after registration.This method can guarantee that the verity filling up data, but can be subject to the restriction at data acquisition visual angle and the impact of Registration of Measuring Data and fusion accuracy.Computer graphical, a cloud sparse data cavity is filled up by the data fusion algorithms such as the research field Usual Curved Surfaces matching such as computer vision and virtual reality, interpolation.The method is based on certain assumed condition more, and the reliability filling up data is relatively difficult to ensure card.In facade geometry reconstruction, many researchs have the knowledge such as repetition, symmetry according to fabric structure and synthesize occlusion area building facade geometry, such as building facade structures rule that is that utilize priori or that refined by a certain amount of known sample, rationally know the building facade geometry of the part that is blocked by inference.The advantage of this method be utilize existing priori or from available data excavate rules guide occlusion area geometry rebuild, but it be limited in that the building facade structures of occlusion area has to comply with the rule of reasoning.
Most of building facades take into account regular and irregular geometry arrangement, and bottom usually change, be also the region frequently blocked.Present invention is generally directed to, in no data or the enough situations of data deficiencies, solve occlusion area building facade geometry Problems of Reconstruction.
Summary of the invention
The present invention provides the occlusion area building facade method for reconstructing of a kind of ground LiDAR and image data fusion, the method is on the initial facade model basis utilizing image refinement cloud data to rebuild, first assume that all occlusion areas are consistent with regularly arranged, speculate the facade geometry of occlusion area with this understanding, then verify and detect the reconstructed results of irregular codes with cloud data, it is to avoid the insecure facade geometry of occlusion area is rebuild.
The present invention is achieved mainly by following technical proposals:
The occlusion area building facade method for reconstructing of a kind of ground LiDAR and image data fusion, it is characterised in that comprise the following steps:
Step 1, LiDAR point cloud data reconstruction building facade initial model, including following sub-step:
Step 1.1, calculates the normal vector of LiDAR data point, according to data point normal vector parallel ground segmentation building facade cloud data, and with RANSAC excluding gross error point；Major part facade geometry distance building facade certain distance, in facade cutting procedure, these data points are filtered, and are rendered as hole；
Step 1.2, by hole Detection and Extraction building facade geometry, the angular coordinate of artificial semi-automatic acquisition facade cloud data leak, form the rectangle closed or the polygon original reconstruction model as facade geometry；
Step 2, the building facade initial model in conjunction with image data is refined, and comprises the steps:
Step 2.1, utilizes canny operator detection image edge, extracts straight line with hough conversion on this basis；
Step 2.2, under image direction element known conditions, projects on image by the building facade initial model rebuild in step 1, the corresponding image limit of matching initial facade geometric model limit and extraction；
Step 2.3, in model limit and image limit matching process, except distance and direction retrain, add the cloud data through window and select best corresponding image limit as constraints, solve in the field of search, meet a plurality of candidate limit Problems existing under distance and direction restraint condition；
Will transmit through the some cloud of window and project on image, optimal images limit should be positioned at a cloud projection and the projection of non-dots cloud is had a common boundary, consider the some cloud project migration that image direction element error causes, selecting image limit two edge point cloud number difference to be best coupling image limit to the maximum, the some cloud of described window includes the cloud data of internal window frame, curtain and internal reflection；
Step 2.4, mates the best image limit and projects to building facade, obtains accurate building facade geometry；
Step 3, building facade structures rule analysis and occlusion area geometry speculate, comprise the steps:
Step 3.1, classifies to the reconstruction building facade geometry refined in step 2, carries out row, column sequence according to geometry position coordinates, forms 2D image；
According to length of side number and total length, the reconstruction building facade geometry refined being classified, the process of classification is to reconstruction geometry labeling process；The position coordinates of each geometry is the coordinate of its shape geometric center point, carries out column and row labelling according to x and the y of position coordinates, finds out the geometry of same row, column, then row, column is sorted, and forms 2D image；
Step 3.2, the corresponding facade geometry in each row, column cross point, if cross point does not record facade geometry, corresponding row, column is the deletion sites that facade geometry speculates；
Step 3.3, based on the template matching method of facade geometry four neighborhood, with the shape of facade geometry be sized to match measure, the facade geometry that occlusion area is possible is speculated；
Step 4, utilizes reasonability and the reliability of cloud data checking occlusion area geometry.
At the occlusion area building facade method for reconstructing of above-mentioned a kind of ground LiDAR and image data fusion, in described step 4, the reasonability of cloud data checking occlusion area geometry supposition and reliability is utilized to comprise the steps:
Step 4.1, arrives the cloud data of facade geometry through shelter gap and the cloud data through window is split and cluster；
Step 4.2, it is judged that the matching degree of facade geometry correspondence cloud data and estimation result；For the facade geometry of arbitrary prediction, calculate cloud data and speculate facade geometry registration K1And the degree of overlapping K of some cloud boundary rectangle and supposition facade geometry area2；
K1=D1/ D formula one
D is the cloud data that facade geometry is corresponding, D1For falling into the cloud data speculating facade range of geometries；
K2=S1/ S formula two
S is facade geometry correspondence cloud data boundary rectangle area, S1For the overlapping area with supposition facade geometry；
Work as K1And K2During more than certain threshold value, thus it is speculated that result is considered as reliable.
Therefore, present invention have the advantage that utilize image data refine cloud data rebuild initial facade geometric model, in model limit and image limit matching process, cloud data is utilized to solve the problem that there are multiple candidate imagery limits in the field of search, obtain best corresponding image limit, effectively improve the facade geometry skew that laser scanner resolution causes.Simultaneously, lack and incorrect situation for the geometry being insufficient to cause by cloud data in reconstruction model, first meet according to facade geometry and assume rule, four neighborhood template matching methods are adopted to speculate position and the type of occlusion area geometry, then verify the reasonability of reasoning with cloud data, improve the reliability that occlusion area facade is rebuild.
Accompanying drawing explanation
Fig. 1 is inventive algorithm schematic flow sheet.
Fig. 2 a is four neighborhood template matching schematic diagrams (facade geometry 2D images).
Fig. 2 b is four neighborhood template matching schematic diagrams (disappearance geometry four neighborhoods).
Fig. 2 c is four neighborhood template matching schematic diagrams (four neighborhood templates).
Fig. 2 d is four neighborhoods template matching schematic diagram (matching result).
Detailed description of the invention
By the examples below, and in conjunction with accompanying drawing, technical scheme is described in further detail.
Gather building facade LiDAR and image data, be redeveloped into embodiment with the facade window that trees are blocked:
Step 1.LiDAR cloud data rebuilds building facade initial model.
Terrestrial Laser scanner RigelVZ-400 is used for gathering experimental data, and including a cloud and image data, the sampling interval of cloud data is 0.046 °, and image is sized to 4288x2848 pixel, and the registration of some cloud and image data has completed, and image direction element is known.
Point cloud number is 1,830,000, and being positioned at blocking before building mainly has trees, pedestrian, vehicle, telephone booth etc., and blocking of trees opposite is maximum, and the geometry of building facade mainly has window, door and balcony.
The initial facade geometric model of building is obtained through the extraction of facade cloud data and the detection of artificial semi-automatic hole.
Step 2. is refined in conjunction with the building facade initial model of image data.
First, detect image edge with canny operator and image straight line is extracted in hough conversion.
Secondly, initial facade model is projected on image, and with distance and angle conditions restricted selection candidate's window limit, this experimental selection angle threshold is 5 °, and distance threshold is 10 pixels.
Finally, the best is mated image limit and projects to building facade, the facade geometric model after being refined,
Step 3, building facade structures rule analysis and occlusion area geometry speculate.
Step 4, utilizes reasonability and the reliability of cloud data checking occlusion area geometry.
Specific embodiment described herein is only to present invention spirit explanation for example.Described specific embodiment can be made various amendment or supplements or adopt similar mode to substitute by those skilled in the art, but without departing from the spirit of the present invention or surmount the scope that appended claims is defined.
Claims (2)
1. the occlusion area building facade method for reconstructing of a ground LiDAR and image data fusion, it is characterised in that comprise the following steps:
Step 1, LiDAR point cloud data reconstruction building facade initial model, including following sub-step:
Step 1.1, calculates the normal vector of LiDAR data point, according to data point normal vector parallel ground segmentation building facade cloud data, and with RANSAC excluding gross error point；Major part facade geometry distance building facade certain distance, in facade cutting procedure, these data points are filtered, and are rendered as hole；
Step 1.2, by hole Detection and Extraction building facade geometry, the angular coordinate of artificial semi-automatic acquisition facade cloud data leak, form the rectangle closed or the polygon original reconstruction model as facade geometry；
Step 2, the building facade initial model in conjunction with image data is refined, and comprises the steps:
Step 2.1, utilizes canny operator detection image edge, extracts straight line with hough conversion on this basis；
Step 2.2, under image direction element known conditions, projects on image by the building facade initial model rebuild in step 1, the corresponding image limit of matching initial facade geometric model limit and extraction；
Step 2.3, in model limit and image limit matching process, except distance and direction retrain, add the cloud data through window and select best corresponding image limit as constraints, solve in the field of search, meet a plurality of candidate limit Problems existing under distance and direction restraint condition；
Will transmit through the some cloud of window and project on image, optimal images limit should be positioned at a cloud projection and the projection of non-dots cloud is had a common boundary, consider the some cloud project migration that image direction element error causes, selecting image limit two edge point cloud number difference to be best coupling image limit to the maximum, the some cloud of described window includes the cloud data of internal window frame, curtain and internal reflection；
Step 2.4, mates the best image limit and projects to building facade, obtains accurate building facade geometry；
Step 3, building facade structures rule analysis and occlusion area geometry speculate, comprise the steps:
Step 3.1, classifies to the reconstruction building facade geometry refined in step 2, carries out row, column sequence according to geometry position coordinates, forms 2D image；
According to length of side number and total length, the reconstruction building facade geometry refined being classified, the process of classification is to reconstruction geometry labeling process；The position coordinates of each geometry is the coordinate of its shape geometric center point, carries out column and row labelling according to x and the y of position coordinates, finds out the geometry of same row, column, then row, column is sorted, and forms 2D image；
Step 3.2, the corresponding facade geometry in each row, column cross point, if cross point does not record facade geometry, corresponding row, column is the deletion sites that facade geometry speculates；
Step 3.3, based on the template matching method of facade geometry four neighborhood, with the shape of facade geometry be sized to match measure, the facade geometry that occlusion area is possible is speculated；
Step 4, utilizes reasonability and the reliability of cloud data checking occlusion area geometry.
2. the occlusion area building facade method for reconstructing of a kind of ground LiDAR according to claim 1 and image data fusion, in described step 4, utilizes the reasonability of cloud data checking occlusion area geometry supposition and reliability to comprise the steps:
Step 4.1, arrives the cloud data of facade geometry through shelter gap and the cloud data through window is split and cluster；
Step 4.2, it is judged that the matching degree of facade geometry correspondence cloud data and estimation result；For the facade geometry of arbitrary prediction, calculate cloud data and speculate facade geometry registration K1And the degree of overlapping K of some cloud boundary rectangle and supposition facade geometry area2；
K1=D1/ D formula one
D is the cloud data that facade geometry is corresponding, D1For falling into the cloud data speculating facade range of geometries；
K2=S1/ S formula two
S is facade geometry correspondence cloud data boundary rectangle area, S1For the overlapping area with supposition facade geometry；
Work as K1And K2During more than certain threshold value, thus it is speculated that result is considered as reliable.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610113150.2A CN105761308B (en) | 2016-02-29 | 2016-02-29 | A kind of occlusion area building facade method for reconstructing of ground LiDAR and image data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610113150.2A CN105761308B (en) | 2016-02-29 | 2016-02-29 | A kind of occlusion area building facade method for reconstructing of ground LiDAR and image data fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105761308A true CN105761308A (en) | 2016-07-13 |
| CN105761308B CN105761308B (en) | 2018-09-07 |
Family
ID=56331520
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610113150.2A Expired - Fee Related CN105761308B (en) | 2016-02-29 | 2016-02-29 | A kind of occlusion area building facade method for reconstructing of ground LiDAR and image data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105761308B (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106327576A (en) * | 2016-08-10 | 2017-01-11 | 周口师范学院 | Urban scene reconstruction method and system |
| CN108090916A (en) * | 2017-12-21 | 2018-05-29 | 百度在线网络技术（北京）有限公司 | For tracking the method and apparatus of the targeted graphical in video |
| CN109215136A (en) * | 2018-09-07 | 2019-01-15 | 百度在线网络技术（北京）有限公司 | A kind of truthful data Enhancement Method, device and terminal |
| CN110008207A (en) * | 2019-03-28 | 2019-07-12 | 武汉大学 | Airborne lidar point cloud data loophole rapid detection method based on density histogram |
| CN111612806A (en) * | 2020-01-10 | 2020-09-01 | 江西理工大学 | Building facade window extraction method and device |
| CN112683221A (en) * | 2020-12-21 | 2021-04-20 | 深圳集智数字科技有限公司 | Building detection method and related device |
| US10984588B2 (en) | 2018-09-07 | 2021-04-20 | Baidu Online Network Technology (Beijing) Co., Ltd | Obstacle distribution simulation method and device based on multiple models, and storage medium |
| CN112798054A (en) * | 2021-03-02 | 2021-05-14 | 济南齐森建筑工程质量检测有限公司 | Window detection equipment |
| US11047673B2 (en) | 2018-09-11 | 2021-06-29 | Baidu Online Network Technology (Beijing) Co., Ltd | Method, device, apparatus and storage medium for detecting a height of an obstacle |
| US11113546B2 (en) | 2018-09-04 | 2021-09-07 | Baidu Online Network Technology (Beijing) Co., Ltd. | Lane line processing method and device |
| US11126875B2 (en) | 2018-09-13 | 2021-09-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and device of multi-focal sensing of an obstacle and non-volatile computer-readable storage medium |
| US11276243B2 (en) | 2018-09-07 | 2022-03-15 | Baidu Online Network Technology (Beijing) Co., Ltd. | Traffic simulation method, device and storage medium |
| CN114332402A (en) * | 2021-12-23 | 2022-04-12 | 中交第二公路勘察设计研究院有限公司 | Ground-based and handheld laser scanning-fused steel bridge simulation pre-assembly method |
| US11307302B2 (en) | 2018-09-07 | 2022-04-19 | Baidu Online Network Technology (Beijing) Co., Ltd | Method and device for estimating an absolute velocity of an obstacle, and non-volatile computer-readable storage medium |
| CN114937123A (en) * | 2022-07-19 | 2022-08-23 | 南京邮电大学 | Building modeling method and device based on multi-source image fusion |
| US11718318B2 (en) | 2019-02-22 | 2023-08-08 | Apollo Intelligent Driving (Beijing) Technology Co., Ltd. | Method and apparatus for planning speed of autonomous vehicle, and storage medium |
| US11780463B2 (en) | 2019-02-19 | 2023-10-10 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method, apparatus and server for real-time learning of travelling strategy of driverless vehicle |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102147812A (en) * | 2011-03-31 | 2011-08-10 | 中国科学院自动化研究所 | Three-dimensional point cloud model-based landmark building image classifying method |
| CN102521884A (en) * | 2011-12-16 | 2012-06-27 | 南京大学 | Three-dimensional roof reconstruction method based on LiDAR data and ortho images |
| US8547374B1 (en) * | 2009-07-24 | 2013-10-01 | Lockheed Martin Corporation | Detection and reconstruction of 3D objects with passive imaging sensors |
-
2016
- 2016-02-29 CN CN201610113150.2A patent/CN105761308B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8547374B1 (en) * | 2009-07-24 | 2013-10-01 | Lockheed Martin Corporation | Detection and reconstruction of 3D objects with passive imaging sensors |
| CN102147812A (en) * | 2011-03-31 | 2011-08-10 | 中国科学院自动化研究所 | Three-dimensional point cloud model-based landmark building image classifying method |
| CN102521884A (en) * | 2011-12-16 | 2012-06-27 | 南京大学 | Three-dimensional roof reconstruction method based on LiDAR data and ortho images |
Non-Patent Citations (5)
| Title |
|---|
| MARTIN KADA等: "3D BUILDING RECONSTRUCTION FROM LIDAR BASED ON A CELL DECOMPOSITION APPROACH", 《CMRT09: OBJECT EXTRACTION FOR 3D CITY MODELS, ROAD DATABASES AND TRAFFIC MONITORING-CONCEPTS, ALGORITHMS, AND EVALUATION》 * |
| NORBERT HAALA等: "An update on automatic 3D building reconstruction", 《ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING》 * |
| SHI PU等: "Building Facade Reconstruction by Fusing Terrestrial Laser Points and Images", 《SENSORS》 * |
| 杨必胜等: "从车载激光扫描数据中提取复杂建筑物立面的方法", 《测绘学报》 * |
| 王俊等: "基于图像匹配-点云融合的建筑物立面三维重建", 《计算机学报》 * |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106327576A (en) * | 2016-08-10 | 2017-01-11 | 周口师范学院 | Urban scene reconstruction method and system |
| CN106327576B (en) * | 2016-08-10 | 2019-03-29 | 周口师范学院 | A kind of City scenarios method for reconstructing and system |
| CN108090916A (en) * | 2017-12-21 | 2018-05-29 | 百度在线网络技术（北京）有限公司 | For tracking the method and apparatus of the targeted graphical in video |
| CN108090916B (en) * | 2017-12-21 | 2019-05-07 | 百度在线网络技术（北京）有限公司 | Method and apparatus for tracking the targeted graphical in video |
| US11113546B2 (en) | 2018-09-04 | 2021-09-07 | Baidu Online Network Technology (Beijing) Co., Ltd. | Lane line processing method and device |
| US11307302B2 (en) | 2018-09-07 | 2022-04-19 | Baidu Online Network Technology (Beijing) Co., Ltd | Method and device for estimating an absolute velocity of an obstacle, and non-volatile computer-readable storage medium |
| US11276243B2 (en) | 2018-09-07 | 2022-03-15 | Baidu Online Network Technology (Beijing) Co., Ltd. | Traffic simulation method, device and storage medium |
| US10984588B2 (en) | 2018-09-07 | 2021-04-20 | Baidu Online Network Technology (Beijing) Co., Ltd | Obstacle distribution simulation method and device based on multiple models, and storage medium |
| CN109215136A (en) * | 2018-09-07 | 2019-01-15 | 百度在线网络技术（北京）有限公司 | A kind of truthful data Enhancement Method, device and terminal |
| US11205289B2 (en) | 2018-09-07 | 2021-12-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method, device and terminal for data augmentation |
| US11519715B2 (en) | 2018-09-11 | 2022-12-06 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method, device, apparatus and storage medium for detecting a height of an obstacle |
| US11047673B2 (en) | 2018-09-11 | 2021-06-29 | Baidu Online Network Technology (Beijing) Co., Ltd | Method, device, apparatus and storage medium for detecting a height of an obstacle |
| US11126875B2 (en) | 2018-09-13 | 2021-09-21 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and device of multi-focal sensing of an obstacle and non-volatile computer-readable storage medium |
| US11780463B2 (en) | 2019-02-19 | 2023-10-10 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method, apparatus and server for real-time learning of travelling strategy of driverless vehicle |
| US11718318B2 (en) | 2019-02-22 | 2023-08-08 | Apollo Intelligent Driving (Beijing) Technology Co., Ltd. | Method and apparatus for planning speed of autonomous vehicle, and storage medium |
| CN110008207B (en) * | 2019-03-28 | 2020-08-07 | 武汉大学 | Airborne L iDAR point cloud data vulnerability rapid detection method based on density histogram |
| CN110008207A (en) * | 2019-03-28 | 2019-07-12 | 武汉大学 | Airborne lidar point cloud data loophole rapid detection method based on density histogram |
| CN111612806A (en) * | 2020-01-10 | 2020-09-01 | 江西理工大学 | Building facade window extraction method and device |
| CN112683221B (en) * | 2020-12-21 | 2022-05-17 | 深圳集智数字科技有限公司 | Building detection method and related device |
| CN112683221A (en) * | 2020-12-21 | 2021-04-20 | 深圳集智数字科技有限公司 | Building detection method and related device |
| CN112798054A (en) * | 2021-03-02 | 2021-05-14 | 济南齐森建筑工程质量检测有限公司 | Window detection equipment |
| CN114332402A (en) * | 2021-12-23 | 2022-04-12 | 中交第二公路勘察设计研究院有限公司 | Ground-based and handheld laser scanning-fused steel bridge simulation pre-assembly method |
| CN114332402B (en) * | 2021-12-23 | 2024-04-02 | 中交第二公路勘察设计研究院有限公司 | Steel bridge simulation pre-assembly method integrating ground type and hand-held laser scanning |
| CN114937123A (en) * | 2022-07-19 | 2022-08-23 | 南京邮电大学 | Building modeling method and device based on multi-source image fusion |
| CN114937123B (en) * | 2022-07-19 | 2022-11-04 | 南京邮电大学 | Building modeling method and device based on multi-source image fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105761308B (en) | 2018-09-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105761308A (en) | Ground LiDAR and image data fused occlusion region building facade reconstruction method | |
| Zhang et al. | Learning signed distance field for multi-view surface reconstruction | |
| Cheng et al. | 3D building model reconstruction from multi-view aerial imagery and lidar data | |
| Zhou et al. | Seamless fusion of LiDAR and aerial imagery for building extraction | |
| Gamba et al. | Improving urban road extraction in high-resolution images exploiting directional filtering, perceptual grouping, and simple topological concepts | |
| CN102136155B (en) | Object elevation vectorization method and system based on three dimensional laser scanning | |
| Habib et al. | Generation of complex polyhedral building models by integrating stereo-aerial imagery and lidar data | |
| Becker | Generation and application of rules for quality dependent façade reconstruction | |
| Yan et al. | Automatic construction of 3-D building model from airborne LiDAR data through 2-D snake algorithm | |
| Ceylan et al. | Factored facade acquisition using symmetric line arrangements | |
| Becker et al. | Refinement of building fassades by integrated processing of lidar and image data | |
| Nex et al. | Automatic roof outlines reconstruction from photogrammetric DSM | |
| Bethmann et al. | Object-based multi-image semi-global matching–concept and first results | |
| CN110390256A (en) | A kind of asphalt pavement crack extracting method | |
| Yuan et al. | Sdv-loam: Semi-direct visual-lidar odometry and mapping | |
| Wang et al. | A method for detecting windows from mobile LiDAR data | |
| EP3918570B1 (en) | Localization of elements in the space | |
| Li et al. | WHU-stereo: A challenging benchmark for stereo matching of high-resolution satellite images | |
| Saxena et al. | 3-d reconstruction from sparse views using monocular vision | |
| Chen et al. | Range image segmentation for modeling and object detection in urban scenes | |
| Zhang et al. | Automatic terrain extraction using multiple image pair and back matching | |
| Sreevalsan-Nair et al. | Contour extraction in buildings in airborne lidar point clouds using multiscale local geometric descriptors and visual analytics | |
| Previtali et al. | Automatic façade segmentation for thermal retrofit | |
| CN113838005B (en) | Intelligent identification and three-dimensional reconstruction method and system for rock mass fracture based on dimension conversion | |
| Noh et al. | Highly Dense 3D Surface Generation Using Multi‐image Matching |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180907 Termination date: 20190228 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |